Preprint
Oct 2026
Text-to-Image Generative Modeling Without Language Pretraining
Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for strong T2I generation. We introduce Halcyon, a family of early-fusion multimodal autoregressive models pretrained entirely from scratch on GPIC, a datase...
Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas et al.
· 0 citations